Can Decentralized Learning be more robust than Federated Learning?. (arXiv:2303.03829v1 [cs.LG])

Decentralized Learning (DL) is a peer--to--peer learning approach that allows
a group of users to jointly train a machine learning model. To ensure
correctness, DL should be robust, i.e., Byzantine users must not be able to
tamper with the result of the collaboration. In this paper, we introduce two
\textit{new} attacks against DL where a Byzantine user can: make the network
converge to an arbitrary model of their choice, and exclude an arbitrary user
from the learning process. We demonstrate …

attacks collaboration converge correctness decentralized federated learning machine machine learning network result train